{"id":"https://openalex.org/W4407197371","doi":"https://doi.org/10.1145/3669940.3707266","title":"Design and Operation of Shared Machine Learning Clusters on Campus","display_name":"Design and Operation of Shared Machine Learning Clusters on Campus","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407197371","doi":"https://doi.org/10.1145/3669940.3707266"},"language":"en","primary_location":{"id":"doi:10.1145/3669940.3707266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3669940.3707266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027039140","display_name":"Kaiqiang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Kaiqiang Xu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024828557","display_name":"Decang Sun","orcid":"https://orcid.org/0000-0003-3442-4656"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Decang Sun","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446070","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-9883-2400"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085112687","display_name":"Zhenghang Ren","orcid":"https://orcid.org/0000-0002-8779-4768"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenghang Ren","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063239975","display_name":"Xinchen Wan","orcid":"https://orcid.org/0000-0001-6503-5309"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xinchen Wan","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052148248","display_name":"Xudong Liao","orcid":"https://orcid.org/0000-0002-8380-1879"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xudong Liao","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101665850","display_name":"Zilong Wang","orcid":"https://orcid.org/0000-0003-3184-4081"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zilong Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071584772","display_name":"Junxue Zhang","orcid":"https://orcid.org/0000-0001-6926-7801"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junxue Zhang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438001","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0003-2587-6028"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5027039140"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":18.5792,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98866011,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14484","display_name":"Technology and Data Analysis","score":0.963100016117096,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.9369000196456909,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6857427358627319},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4068760275840759},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3511524200439453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6857427358627319},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4068760275840759},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3511524200439453}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3669940.3707266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3669940.3707266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-145289","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-145289","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1274456251","display_name":null,"funder_award_id":"Hong Kong RGC TRS T41-603/20-R","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2112168774","https://openalex.org/W2164740236","https://openalex.org/W2751343396","https://openalex.org/W3132460984","https://openalex.org/W3186339322","https://openalex.org/W4290991649","https://openalex.org/W4312933868","https://openalex.org/W4318541676","https://openalex.org/W4387321109"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,96,105,123,142],"large":[4],"machine":[5],"learning":[6],"(ML)":[7],"models":[8],"has":[9],"driven":[10],"universities":[11],"worldwide":[12],"to":[13,46,60,126,136],"invest":[14],"heavily":[15],"in":[16],"GPU":[17,37,63],"clusters.":[18],"Effectively":[19],"sharing":[20,75],"these":[21],"resources":[22,135],"among":[23,50],"multiple":[24],"users":[25],"is":[26],"essential":[27],"for":[28,72],"maximizing":[29],"both":[30],"utilization":[31],"and":[32,87,108,117,140],"accessibility.":[33],"However,":[34],"managing":[35],"shared":[36,62,128],"clusters":[38],"presents":[39],"significant":[40],"challenges,":[41],"ranging":[42],"from":[43,111],"system":[44],"configuration":[45],"fair":[47],"resource":[48,74,89],"allocation":[49],"users.":[51],"This":[52],"paper":[53],"introduces":[54],"SING,":[55],"a":[56,93],"full-stack":[57],"solution":[58],"tailored":[59],"simplify":[61],"cluster":[64,130],"management.":[65],"Aimed":[66],"at":[67],"addressing":[68],"the":[69,103,138],"pressing":[70],"need":[71],"efficient":[73],"with":[76],"limited":[77],"staffing,":[78],"SING":[79],"enhances":[80],"operational":[81],"efficiency":[82],"by":[83],"reducing":[84],"maintenance":[85],"costs":[86],"optimizing":[88],"utilization.":[90],"We":[91],"provide":[92],"comprehensive":[94],"overview":[95],"its":[97],"four":[98],"extensible":[99],"architectural":[100],"layers,":[101],"explore":[102],"features":[104],"each":[106],"layer,":[107],"share":[109],"insights":[110],"real-world":[112],"deployment,":[113],"including":[114],"usage":[115],"patterns":[116],"incident":[118],"management":[119],"strategies.":[120],"As":[121],"part":[122],"our":[124],"commitment":[125],"advancing":[127],"ML":[129],"management,":[131],"we":[132],"open-source":[133],"SING's":[134],"support":[137],"development":[139],"operation":[141],"similar":[143],"systems.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}